Job Search and Career Advice Platform

Enable job alerts via email!

AI Solutions Architect: LLM & Inference Deployments

NVIDIA

Singapore

Hybrid

SGD 120,000 - 160,000

Full time

21 days ago

Generate a tailored resume in minutes

Land an interview and earn more. Learn more

Job summary

A leading tech company in Singapore seeks a skilled NIM Solution Architect to drive the implementation of AI solutions, optimize models, and support customers using advanced NVIDIA technologies. Candidates must have 7+ years of experience and a strong background in deploying large language models. Proficiency in Python and C++ is essential, along with experience in DevOps/MLOps. The role offers a collaborative environment focused on innovation and impact.

Qualifications

  • 7+ years of experience in relevant roles.
  • Proven experience in deploying and optimizing large language models.
  • Strong programming skills in Python or C++, with knowledge of inference frameworks.

Responsibilities

  • Drive implementation and deployment of NIM solutions.
  • Build and implement agentic AI tailored to customer scenarios using NIMs.
  • Collaborate with teams to develop AI solutions portfolio.

Skills

Deploying large language models
Python programming
C++ programming
DevOps
MLOps
Problem-solving
Collaborative skills
AI workflow development
CUDA optimization

Education

Bachelor's degree in Computer Science or relevant field

Tools

TensorRT
ONNX Runtime
PyTorch
Docker
Git
CI/CD practices
Job description
A leading tech company in Singapore seeks a skilled NIM Solution Architect to drive the implementation of AI solutions, optimize models, and support customers using advanced NVIDIA technologies. Candidates must have 7+ years of experience and a strong background in deploying large language models. Proficiency in Python and C++ is essential, along with experience in DevOps/MLOps. The role offers a collaborative environment focused on innovation and impact.
Get your free, confidential resume review.
or drag and drop a PDF, DOC, DOCX, ODT, or PAGES file up to 5MB.